Torch自动求导（）

import torch

x = torch.ones((2,2),requires_grad=True)
print("x>>>",x)

y = x+2
z = y*y*3
out = z.mean()
print("out>>>",out)
out.backward()
print("x.grad>>>",x.grad)

 

输出结果

x>>> tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
out>>> tensor(27., grad_fn=<MeanBackward0>)
x.grad>>> tensor([[4.5000, 4.5000],
        [4.5000, 4.5000]])